4 papers
A Systematic Reproducibility Study of BSARec for Sequential Recommendation
Jan Hutter, Hua Chang Bakker, Stan Fris +2
In sequential recommendation (SR), the self-attention mechanism of Transformer-based models acts as a low-pass filter, limiting their ability to capture high-frequency signals that…
On the Reproducibility of "FairCLIP: Harnessing Fairness in Vision-Language Learning''
Hua Chang Bakker, Stan Fris, Angela Madelon Bernardy +1
We investigated the reproducibility of FairCLIP, proposed by Luo et al. (2024), for improving the group fairness of CLIP (Radford et al., 2021) by minimizing image-text similarity…
Keep your distance: learning dispersed embeddings on
Evgeniia Tokarchuk, Hua Chang Bakker, Vlad Niculae
Learning well-separated features in high-dimensional spaces, such as text or image embeddings, is crucial for many machine learning applications. Achieving such separation can be e…
A Simpler Alternative to Variational Regularized Counterfactual Risk Minimization
Hua Chang Bakker, Shashank Gupta, Harrie Oosterhuis
Variance regularized counterfactual risk minimization (VRCRM) has been proposed as an alternative off-policy learning (OPL) method. VRCRM method uses a lower-bound on the -diver…